shine-ab-test-plan

Define AB test plans with hypothesis, metrics, MDE, sample size, and rollout steps.

1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/diShine-digital-agency/SHINE-Code-System --skill shine-ab-test-plan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shine-ab-test-plan
Source: https://github.com/diShine-digital-agency/SHINE-Code-System/tree/main/skills/shine-ab-test-plan
Command: npx skills add https://github.com/diShine-digital-agency/SHINE-Code-System --skill shine-ab-test-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams design rigorous AB test plans, including hypothesis, metrics, minimum detectable effect, sample size, duration, guardrails, and rollout.

Core Features & Use Cases

  • Hypothesis and metrics: Define a test hypothesis and a primary metric with success criteria.
  • Power calculations & planning: Compute MDE, required sample size, and recommended duration for one or more variants.
  • Rollout rules & guardrails: Outline decision rules and safety guardrails for deployment and analysis.

Quick Start

Draft a complete AB test plan for a feature idea, including hypothesis, metrics, MDE, sample size, duration, guardrails, and rollout steps.

Frequently Asked Questions about shine-ab-test-plan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an A/B test plan with sample size and statistical power calculations?

To create an A/B test plan, you define a clear hypothesis, primary metric, and minimum detectable effect (MDE). This allows you to compute the required sample size and recommended test duration to ensure your experiment achieves adequate statistical power.

What guardrails should I include when designing an experiment for product or marketing?

Experiment guardrails should include predefined decision rules, baseline metrics, analysis methods, and safety mitigations. These guardrails outline specific rollout steps and monitoring criteria across variants to prevent negative impacts during deployment.

What is a minimum detectable effect (MDE) and why is it needed for A/B testing?

A minimum detectable effect (MDE) is the smallest improvement in your primary metric that your A/B test is designed to capture statistically. Defining the MDE is needed to calculate the required sample size and determine the experiment duration.

How do I determine the required duration for an experiment with multiple variants?

You determine experiment duration by calculating the required sample size based on your primary metric, MDE, and statistical power. This calculation ensures you gather enough data across all variants to reach a statistically valid conclusion.

Can I use this A/B test planning approach for both product and marketing experiments?

Yes, you can apply this A/B test planning approach to both product and marketing experiments. It structures your hypothesis, measurement criteria, and rollout rules to ensure clear evaluation across different variants in either context.